Sanctuary

Open-source security layer that wraps AI coding agents with egress control and an audit trail

Desktopfree

Sanctuary is an open-source security layer that wraps an existing AI coding agent, such as Claude Code or Cursor, with policy gates, operator-held encryption keys, and an audit trail, installed with a single command. On macOS it can enforce operating-system-level network egress control through a signed system extension, and it provides a local dashboard for reviewing agent activity, aimed at developers who want oversight of what their AI coding agent does and sends over the network.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Sanctuary - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Sanctuary to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Sanctuary (or something else) actually fits.

Try a problem